feat(ingester): support metadata updates only #73
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Added `updateDocumentsMetadata()` to update metadata (and `source` column) in-place by `uniqueId` without re-embedding or replacing content.
- vectorStoreUtils.ts
- `findChunksToUpdateAndRemove()` now returns three buckets: `contentChanged`, `metadataOnlyChanged`, and `chunksToRemove`.
- `updateVectorStore()` now:
- Removes documents that no longer exist.
- Upserts content-changed documents via `addDocuments()` (re-embeds as before).
- Updates metadata-only documents via `updateDocumentsMetadata()` (no re-embed).
- Tests
- Updated `ingesters/__tests__/vectorStoreUtils.test.ts` to cover content-changed vs metadata-only cases; all tests pass.
enitrat
force-pushed
the
feat-ingester-partial-update
branch
from
8cef519 to
781742f
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Ingestion: Incremental Vector Store Updates (TypeScript)
updateDocumentsMetadata()to update metadata (andsourcecolumn) in-place byuniqueIdwithout re-embedding or replacing content.findChunksToUpdateAndRemove()now returns three buckets:contentChanged,metadataOnlyChanged, andchunksToRemove.updateVectorStore()now:addDocuments()(re-embeds as before).updateDocumentsMetadata()(no re-embed).ingesters/__tests__/vectorStoreUtils.test.tsto cover content-changed vs metadata-only cases; all tests pass.